Donut vs Aya Vision
Donut is faster. Only Donut supports Forms. Only Aya Vision supports Multilingual.
Donutnaver/donut | Aya Visioncohere/aya-vision | |
|---|---|---|
| Type | Open source | Open source |
| Price | 1 credit / page | 1 credit / page |
| Per 1,000 pages | $1.00 | $1.00 |
| Typical speed | 1.0 s / page | 3.0 s / page |
| Best for | Receipt and form fields after fine-tuning | Multilingual image questions |
| Inputs | images | images |
| Languages | English, Chinese, Japanese, Korean | 23 languages |
| Max pages per request | 100 | 50 |
| Tables | No | No |
| Handwriting | No | No |
| Math | No | No |
| Bounding boxes | No | No |
| Confidence | No | No |
| Forms | ✓ Yes | No |
| Multilingual | No | ✓ Yes |
| On OCRRouter | Available | Available |
Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.
What each one is
Donut
OCR-free document understanding model. Fine-tuned for receipts, forms and document Q&A.
Donut detailsAya Vision
Cohere's open-weight multilingual vision models (8B and 32B, March 2025).
Aya Vision detailsTry both on your own file
Run the file once with each model and compare the output.
PDF, PNG, JPG, WebP, HEIC. Up to 10 files at onceNo file?
Use one, fall back to the other
{"model": "naver/donut","fallbacks": ["cohere/aya-vision"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Donut vs Command A VisionDonut vs LLaVA-OneVisionGOT-OCR 2.0 vs Aya VisionNougat vs Aya VisionDonut vs UnstructuredDonut vs OpenOCRNanonets-OCR vs DonutKraken vs Donut
Donut alternativesAya Vision alternativesBest OCR models in 2026